From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001
From: Kawrakow <48489457+ikawrakow@users.noreply.github.com>
Date: Sat, 27 Jul 2024 07:55:01 +0200
Subject: Merge mainline llama.cpp (#3)

* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
---
 ggml-sycl/common.cpp | 53 ----------------------------------------------------
 1 file changed, 53 deletions(-)
 delete mode 100644 ggml-sycl/common.cpp

(limited to 'ggml-sycl/common.cpp')

diff --git a/ggml-sycl/common.cpp b/ggml-sycl/common.cpp
deleted file mode 100644
index e878f4f5..00000000
--- a/ggml-sycl/common.cpp
+++ /dev/null
@@ -1,53 +0,0 @@
-//
-// MIT license
-// Copyright (C) 2024 Intel Corporation
-// SPDX-License-Identifier: MIT
-//
-
-//
-// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-// See https://llvm.org/LICENSE.txt for license information.
-// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-//
-
-#include "common.hpp"
-
-int get_current_device_id() {
-  return dpct::dev_mgr::instance().current_device_id();
-}
-
-void* ggml_sycl_host_malloc(size_t size) try {
-  if (getenv("GGML_SYCL_NO_PINNED") != nullptr) {
-    return nullptr;
-  }
-
-  void* ptr = nullptr;
-  // allow to use dpct::get_in_order_queue() for host malloc
-  dpct::err0 err = CHECK_TRY_ERROR(
-      ptr = (void*)sycl::malloc_host(size, dpct::get_in_order_queue()));
-
-  if (err != 0) {
-    // clear the error
-    fprintf(
-        stderr,
-        "WARNING: failed to allocate %.2f MB of pinned memory: %s\n",
-        size / 1024.0 / 1024.0,
-        "syclGetErrorString is not supported");
-    return nullptr;
-  }
-
-  return ptr;
-} catch (sycl::exception const& exc) {
-  std::cerr << exc.what() << "Exception caught at file:" << __FILE__
-            << ", line:" << __LINE__ << std::endl;
-  std::exit(1);
-}
-
-void ggml_sycl_host_free(void* ptr) try {
-  // allow to use dpct::get_in_order_queue() for host malloc
-  SYCL_CHECK(CHECK_TRY_ERROR(sycl::free(ptr, dpct::get_in_order_queue())));
-} catch (sycl::exception const& exc) {
-  std::cerr << exc.what() << "Exception caught at file:" << __FILE__
-            << ", line:" << __LINE__ << std::endl;
-  std::exit(1);
-}
-- 
cgit v1.2.3